Optimization Algorithm Research Articles

Operating condition design with a Bayesian optimization approach for pharmaceutical intermediate batch concentration

In the synthesis of pharmaceutical intermediates, concentration is commonly employed to separate the product and recycle the solvents. To achieve a cost-effective manufacturing, operating parameters shall be adjusted over time, which could traditionally be achieved based on dynamic simulation, but with significant computation cost. In this work, we introduced a Bayesian optimization approach to design the optimal operating condition of a pharmaceutical intermediate in the production of Lamivudine. Using a Gaussian process regression as the surrogate model, the approach tremendously reduced the computational cost in searching for the optimal design. In comparison to other commonly used intelligent optimization algorithms, the results demonstrate that the presented approach confers evident advantages, especially in reducing the tendency of getting trapped in local optima and in improving the speed of convergence to an optimal solution.

Enhancing Support Vector Machine Performance: A Hybrid Approach with Davidon-Fletcher-Powell Algorithm and Elephant Herding Optimization (EHO-DFP) for Parameter Optimization

Support Vector Machines (SVMs) have gained prominence in machine learning for their capability to establish optimal decision boundaries in high-dimensional spaces. SVMs are powerful machine learning models but can encounter difficulties in achieving optimal performance due to challenges such as selecting appropriate kernel parameters, handling uncertain data, and adapting to complex decision boundaries.. This paper introduces a novel hybrid approach to enhance the performance of Support Vector Machines (SVM) through the integration of the Davidon-Fletcher-Powell (DFP) optimization algorithm and Elephant Herding Optimization (EHO) for parameter tuning. SVM, a robust machine learning algorithm, relies on effective hyperparameter selection for optimal performance. The proposed hybrid model synergistically leverages DFP's efficiency in unconstrained optimization and EHO's exploration-exploitation balance inspired by elephant herding behavior. The fusion of these algorithms address the challenges associated with traditional optimization methods. The hybrid model offers improved convergence towards the global optimum. Experimental results demonstrate the efficacy of the approach, showcasing enhanced SVM performance in terms of minimum 3.3% accuracy and 3.4% efficiency. This research contributes to advancing the field of metaheuristic optimization in machine learning, providing a promising avenue for effective parameter optimization in SVM applications.

Application of improved grey wolf model in collaborative trajectory optimization of unmanned aerial vehicle swarm

With the development of science and technology and economy, UAV is used more and more widely. However, the existing UAV trajectory planning methods have the limitations of high cost and low intelligence. In view of this, grey Wolf algorithm is being used to achieve collaborative trajectory optimization of UAV groups. However, it is found that the Grey Wolf optimization algorithm (GWO) has the problem of weak cooperation. In this study, based on the traditional GWO pheromone factor is introduced to improve it.. Aiming at the problem of unstable performance of swarm intelligence optimization algorithm under dynamic threat, deep reinforcement learning is used to optimize the model. An unmanned aerial vehicle swarm trajectory planning model was constructed based on the improved grey wolf algorithm. Through experimental analysis, the optimal fitness value of the improved grey wolf algorithm was lower than 0.43 of the grey wolf algorithm. Compared with other algorithms, the fitness value of this algorithm is significantly reduced and the stability is higher. In complex scenarios, the improved grey wolf algorithm had a trajectory length of 70.51 km and a planning time of 5.92 s, which was clearly superior to other algorithms. The path length planned by the research and design model was 58.476 km, which was significantly smaller than the other three models. The planning time was 5.33 s and the number of path extension points was 46. The indicator values of the Unmanned Aerial Vehicle swarm trajectory planning model designed by this research were all smaller than the other three models. By analyzing the results, the model can achieve low-cost trajectory optimization, providing more reasonable technical support for unmanned aerial vehicle mission execution.

Isogeometric Topology Optimization of Multi-Material Structures under Thermal-Mechanical Loadings Using Neural Networks

An isogeometric topology optimization (ITO) model for multi-material structures under thermal-mechanical loadings using neural networks is proposed. In the proposed model, a non-uniform rational B-spline (NURBS) function is employed for geometric description and analytical calculation, which realizes the unification of the geometry and computational models. Neural networks replace the optimization algorithms of traditional topology optimization to update the relative densities of multi-material structures. The weights and biases of neural networks are taken as design variables and updated by automatic differentiation without derivation of the sensitivity formula. In addition, the grid elements can be refined directly by increasing the number of refinement nodes, resulting in high-resolution optimal topology without extra computational costs. To obtain comprehensive performance from ITO for multi-material structures, a weighting coefficient is introduced to regulate the proportion between thermal compliance and compliance in the loss function. Some numerical examples are given and the validity is verified by performance analysis. The optimal topological structures obtained based on the proposed model exhibit both excellent heat dissipation and stiffness performance under thermal-mechanical loadings.

Machine learning-based prediction model of lower extremity deep vein thrombosis after stroke.

This study aimed to apply machine learning (ML) techniques to develop and validate a risk prediction model for post-stroke lower extremity deep vein thrombosis (DVT) based on patients' limb function, activities of daily living (ADL), clinical laboratory indicators, and DVT preventive measures. We retrospectively analyzed 620 stroke patients. Eight ML models-logistic regression (LR), support vector machine (SVM), random forest (RF), decision tree (DT), neural network (NN), extreme gradient boosting (XGBoost), Bayesian (NB), and K-nearest neighbor (KNN)-were used to build the model. These models were extensively evaluated using ROC curves, AUC, PR curves, PRAUC, accuracy, sensitivity, specificity, and clinical decision curves (DCA). Shapley's additive explanation (SHAP) was used to determine feature importance. Finally, based on the optimal ML algorithm, different functional feature set models were compared with the Padua scale to select the best feature set model. Our results indicated that the RF algorithm demonstrated superior performance in various evaluation metrics, including AUC (0.74/0.73), PRAUC (0.58/0.58), accuracy (0.75/0.77), and sensitivity (0.78/0.80) in both the training set and test set. DCA analysis revealed that the RF model had the highest clinical net benefit. SHAP analysis showed that D-dimer had the most significant influence on DVT, followed by age, Brunnstrom stage (lower limb), prothrombin time (PT), and mobility ability. The RF algorithm can predict post-stroke DVT to guide clinical practice.

Optimization-based stacked machine-learning method for seismic probability and risk assessment of reinforced concrete shear walls

Efficient seismic risk assessment aids decision-makers in formulating citywide risk mitigation plans, providing insights into building performance and retrofitting costs. The complexity of modeling, analysis, and post-processing of the results makes it hard to fast-track the seismic probabilities, and there is a need to optimize the computational time. This research addresses seismic probability and risk assessment of reinforced concrete shear walls (RCSWs) by introducing stacked machine learning (Stacked ML) models based on Bayesian optimization (BO), genetic algorithm (GA), particle swarm optimization (PSO), and gradient-based optimization (GBO) algorithms. The study investigates 4-, to 15-Story RCSWs assuming different bay lengths and soil types to build a comprehensive database based on the incremental dynamic analysis (IDA) subjected to 56 near-field pulse-like and no-pulse records. Having 227,200 and 63,384 data points for a median of IDA curve (MIDA) and seismic probability curve, respectively, the proposed Stacked ML models have shown good performance on curve fitting ability by accuracy of 99.1% and 99.4% for MIDA and seismic fragility curves, respectively. In addition, the proposed models can estimate the mean annual frequency, λ, which is a key parameter in seismic risk assessment of buildings. To provide the results of the study for general buildings, a user-friendly GUI is proposed that facilitates result utilization, offering insights into seismic performance levels, providing the estimated MIDA and seismic failure probability curves, and mean annual frequency calculations for specific performance levels and seismic hazard curves.

Enhancing cyber security: a comprehensive approach to the classification and prediction of significant cyber incidents (SCI) through data mining and variational neural network with fox optimization algorithm

The rapid advancement of technology and the proliferation of IoT devices have rendered cyberspace vulnerable, resulting in Significant Cyber Incidents (SCIs). This paper proposes an Enhancing Cyber security: a Comprehensive Approach to the Classification with Prediction of Significant Cyber Incidents through Data Mining with Variation Neural Network with Fox Optimization Algorithm (ECS-SCI-DM-VNN-FOA). The dataset is split into pre-pandemic and post-pandemic SCI subsets, according to the report from the Center for Strategic and International Studies (CSIS). Adaptive Variation Bayesian Filter (AVBF) is utilized to remove the noise from the input data. Then the preprocessed input data is supplied to the Improved Window Adaptive Gray Level Co-Occurrence Matrix (IWAGM) for feature extraction. The proposed approach is implemented in Python and its efficacy is evaluated under some metrics, like accuracy, precision, recall, FI-score, sensitivity, computational time, recall, and RoC. The proposed ECS-SCI-DM-VNN-FOA gives 24.91%, 23.76% and 25.98% high accuracy and 30.45%, 23.67% and 29.32% high precision compared with the existing methods, like classification with prediction of cyber events utilizing data mining with machine learning (CRP-SML), Cyber risk prediction via social media big data analytics along statistical machine learning (PECI-MUIP), Mining user interaction patterns in the dark web to forecast enterprise cyber occurrences (CTPA-CSCS) respectively.

Economic evaluation of the second-use batteries energy storage system considering the quantification of environmental benefits

The number of retired batteries from electric vehicles continues to grow, which not only puts pressure on battery recycling but also leads to environmental pollution. By replacing the conventional batteries with the second-use batteries in configuring the energy storage system, the investment cost can be effectively reduced, and the issue of retired batteries disposal can be alleviated. In view of this, the paper investigates the quantification of the environmental benefits of second-use batteries, and comprehensively evaluates the second-use batteries energy storage system (SUBESS) in terms of environmental and economic benefits. The energy storage configuration model aimed at maximizing annual net income is developed, and the improved particle swarm optimization algorithm is applied to determine the optimal capacity and power in a photovoltaic (PV) pilot area. Under the same capacity condition, several evaluation indexes are used to compare the economics of the SUBESS with the conventional batteries energy storage system (CBESS). The results show that: (1) Compared to end-of-life disposal of batteries, secondary utilization will yield greater environmental benefits. (2) When the cost per unit capacity of the SUBESS is lower than 63.99 % of the CBESS, the economy of the SUBESS is better than that of the CBESS. Finally, targeted suggestions are made to further promote the scale development of the retired batteries secondary utilization industry. The research results not only validate the economic feasibility of the SUBESS but also have significant environmental benefits, which can provide a reference for potential investors.

Subspace-based noise covariance estimation for Kalman filter in virtual sensing applications

The accuracy of the Kalman filter in state estimation depends on the knowledge of the process and measurement noise covariances. These are usually treated as tuning parameters and adjusted in a heuristic manner to fine-tune the state predictions. While several methods to identify the noise covariance from data exist, some require the use of optimization algorithms, or inversion of large matrices, which is numerically inefficient. In this work we explore a direct approach to estimate the covariance of possibly correlated process and measurement noises, which is based on subspace identification. It is shown that the subspace-based method outperforms the established autocovariance least-squares scheme and provides a good initial guess on the noise covariance in case the system is subjected to model errors. We validate the proposed scheme on a laboratory experiment, where it is shown that the predictions of the system outputs at sensor locations that are not used as observations in the identification procedure match well with the actual measurements.

OPTIMAL: Titration of anti-IL5 biologics in severe asthma - An open label randomised controlled trial.

Anti-interleukin 5 (anti-IL5) biologics effectively reduce exacerbations and the need for maintenance oral corticosteroids (mOCS) in severe eosinophilic asthma. However, it is unknown how long anti-IL5 treatment should be continued. Data from clinical trials indicate a gradual but variable loss of control after treatment cessation. In this pilot study of titration, we evaluated a dose-titration algorithm in patients who had achieved clinical control on an anti-IL5 biologic. In this open-label randomised controlled trial conducted over 52 weeks, patients with clinical control (no exacerbations or mOCS) on anti-IL5 treatment were randomised to continue with unchanged intervals or have dosing intervals adjusted according to a titration algorithm that gradually extended dosing intervals and reduced them again at signs of loss of disease control. The OPTIMAL algorithm was designed to down-titrate dosing until signs of loss of control, to enable assessment of the longest dosing interval possible. Among 73 patients enrolled, 37 patients were randomised to the OPTIMAL titration arm; 78% of patients tolerated down-titration of treatment. Compared to the control arm, the OPTIMAL arm tended to have more exacerbations during the study (32% versus 17% (p=0.13)). There were no severe adverse events related to titration, and lung function and symptoms scores remained stable and comparable in both study arms throughout. This study serves as a proof-of-concept for titration of anti-IL5 biologics in patients with severe asthma with clinical control on treatment, and the OPTIMAL algorithm provides a potential framework for individualising dosing intervals in the future.

Developing the hybrid BIM-BEM and jellyfish search optimization system for optimizing energy consumption and building installation costs

In recent years, the use of Building Information Modeling (BIM) with Building Energy Modeling (BEM) has become the primary research focus for reducing the energy consumption of buildings in the planning and operational phases. The combination of BIM and BEM offers advantages for the various phases of a construction project. However, there are currently very few studies that can integrate multi-objective optimization algorithms into the BIM-BEM process to achieve automatic optimization and effectively manage many aspects of building development. In this study, an EnergyPlus integrated multi-objective jellyfish search (EP-MOJSO) system was developed, utilizing an optimization algorithm to find the best thermal insulation layers for an Aluminum composite material (ACM) wall. The goal is to reduce the energy consumption and total cost in a BIM-BEM environment. In the case study, the authors successfully applied the system to a real building, resulting in a 10.7% reduction in total cost and a 65 kWh/m2/year reduction in EUI. It is expected that the results of the study will open up new ways of using algorithms for multi-criteria optimization in BIM models to optimize various project factors such as energy and total cost and thus make an important contribution to sustainable building design.

Enhanced botnet detection in IoT networks using zebra optimization and dual-channel GAN classification

The Internet of Things (IoT) permeates various sectors, including healthcare, smart cities, and agriculture, alongside critical infrastructure management. However, its susceptibility to malware due to limited processing power and security protocols poses significant challenges. Traditional antimalware solutions fall short in combating evolving threats. To address this, the research work developed a feature selection-based classification model. At first stage, a preprocessing stage enhances dataset quality through data smoothing and consistency improvement. Feature selection via the Zebra Optimization Algorithm (ZOA) reduces dimensionality, while a classification phase integrates the Graph Attention Network (GAN), specifically the Dual-channel GAN (DGAN). DGAN incorporates Node Attention Networks and Semantic Attention Networks to capture intricate IoT device interactions and detect anomalous behaviors like botnet activity. The model's accuracy is further boosted by leveraging both structural and semantic data with the Sooty Tern Optimization Algorithm (STOA) for hyperparameter tuning. The proposed STOA-DGAN model achieves an impressive 99.87% accuracy in botnet activity classification, showcasing robustness and reliability compared to existing approaches.

Two‐stage algorithm for traffic signal optimization and web‐service system development

Two‐stage algorithm for traffic signal optimization and web‐service system development

Assessment of Hull and Propeller Performance Degradation Based on TSO-GA-LSTM

Evaluating the degradation of hull and ship performance and exploring their degradation pathways is crucial for developing scientific and reasonable ship maintenance plans. This paper proposes a two-stage optimization (TSO) algorithm that combines the Genetic Algorithm (GA) and Long Short-Term Memory (LSTM) network, capable of simultaneously optimizing input features and model parameters to enhance the accuracy and generalization ability of speed prediction models. Additionally, a performance degradation assessment method based on speed loss is provided, aimed at evaluating the degradation of hull and propeller performance, as well as extracting the performance degradation paths. The results indicated that the proposed TSO-LSTM-GA algorithm significantly outperformed existing baseline models. Furthermore, the provided performance degradation assessment method demonstrated certain effectiveness on the target ship data, with a measured degradation rate of 0.00344 kn/d and a performance degradation of 9.569% over 478 days, corresponding to an annual speed loss of 1.257 kn.

A data-driven model for predicting fatigue performance of high-strength steel wires based on optimized XGBOOST

Fatigue damage to high-strength steel wires in cable-stayed bridges can significantly compromise bridge reliability. Previous studies have primarily focused on isolated factors such as corrosion rate or stress ratio, failing to capture the complex interactions among multiple variables. Consequently, a few researchers have developed data-driven models using machine learning methods. However, these unoptimized models exhibit limited prediction performance and convergence speed, and lack in-depth analysis of feature effects on the models. To address these shortcomings, this study combines the Gray Wolf Optimization (GWO) algorithm with the XGBoost model to create a data-driven approach for predicting the fatigue performance of high-strength steel wires under multiple influencing factors. The model is validated using both journal and experimental datasets. Results demonstrate that the proposed GWO-XGBoost model achieves high prediction accuracy (R2 = 0.94) and strong generalization ability, and exhibits rapid convergence in optimizing hyperparameters, outperforming BP neural networks and ridge regression models. Additionally, the study highlights the primary effects of wire mass loss, stress range, and average stress on fatigue life prediction, emphasizing the importance of preventing corrosion and managing stress levels to enhance wire fatigue performance. Analysis of model parameters reveals that alpha and colsample_bytree are critical for maintaining model stability and minimizing error rates, while maximum depth and learning rate significantly impact model complexity and convergence. This suggests that proper tuning of these parameters is essential for ensuring model robustness, efficiency, and generalization ability.

Optimizing neural networks using spider monkey optimization algorithm for intrusion detection system

The constantly changing nature of cyber threats presents unprecedented difficulties for people, institutions, and governments across the globe. Cyber threats are a major concern in today’s digital world like hacking, phishing, malware, and data breaches. These can compromise anyone’s personal information and harm the organizations. An intrusion detection system plays a vital responsibility to identifying abnormal network traffic and alerts the system in real time if any malicious activity is detected. In our present research work Artificial Neural Networks (ANN) layers are optimized with the execution of Spider Monkey Optimization (SMO) to detect attacks or intrusions in the system. The developed model SMO-ANN is examined using publicly available dataset Luflow, CIC-IDS 2017, UNR-IDD and NSL -KDD to classify the network traffic as benign or attack type. In the binary Luflow dataset and the multiclass NSL-KDD dataset, the proposed model SMO-ANN has the maximum accuracy, at 100% and 99%, respectively.

Synthesis of Non-Uniform Spiral Antenna with Low Peak Sidelobe Level Using Enhanced Harris Hawks Optimization Algorithm

Synthesis of Non-Uniform Spiral Antenna with Low Peak Sidelobe Level Using Enhanced Harris Hawks Optimization Algorithm

Optimal design of fractional-order proportional integral derivative controllers for structural vibration suppression

In designing control systems, it is known that fractional-order proportional integral derivative (FOPID) controllers often provide greater flexibility than conventional proportional integral derivative (PID) controllers. This higher level of flexibility has proven to be extremely valuable for various applications such as vibration suppression in structural engineering. In this paper, we study the optimization of FOPID controllers using twelve well-established algorithms to minimize structural responses under seismic excitations. The algorithms include crystal structure algorithm (CryStAl), stochastic paint optimizer, particle swarm optimization, krill herd, harmony search, ant colony optimization, genetic algorithm, grey wolf optimizer, Harris hawks optimization, sparrow search algorithm, hippopotamus optimization algorithm, and duck swarm algorithm. In addition to highlighting the benefits of fractional calculus in structural control, this study provides a detailed analysis of FOPID controllers as well as a brief description of the algorithms used to optimize them. To evaluate the efficiency of the proposed techniques, two building models with different numbers of stories are examined. FOPID controllers are designed based on oustaloup’s approximation and the El Centro earthquake data. Using five well-known metrics, the performances of the developed methods are evaluated against five earthquake scenarios, including the recent earthquake in Turkey. A non-parametric (Friedman) test is also employed to compare the algorithms based on their corresponding vibration reduction. The findings of this analysis show that CryStAl consistently performs better than the other algorithms for both building models, thus resulting in superior vibration suppression.

Research on multi-path optimization problem based on particle swarm optimization algorithm

Research on multi-path optimization problem based on particle swarm optimization algorithm

An effective hybrid meta-heuristic method for the simultaneous batch production and transportation problem in additive manufacturing

One notable advancement in additive manufacturing (AM) is the mobile mini-factory, which uses a truck equipped with an AM machine to produce orders while en-route to customers' locations. This offers potential benefits such as reduced delivery times and storage expenses for companies. This study investigates a simultaneous batch production and transportation problem (denoted by SBPTP) in additive manufacturing. To solve this problem, a mixed integer linear programming (MILP) model is first formulated. Then, to solve large-scale problems, a meta-heuristic method (denoted by SA-CP) combining a simulated annealing (SA) algorithm, an ant colony optimisation algorithm (ACO) and a cutting-plane algorithm is developed, in which the assignment subproblem is dealt with the SA, the simultaneous production and transportation subproblem is dealt with the ACO, and finally the current solution is further improved by the cutting-plane algorithm. Computational experiments are conducted on both randomly generated instances and modified benchmark instances. The results demonstrate that the SA-CP is very effective since it can obtain the solutions with an average relative percentage gap 0.16% on randomly generated instances and −0.09% on modified benchmark instances within less than 180 CPU seconds, compared to those obtained by solving the MILP model directly with CPLEX within 1 h.